Improving NeuroEvolution Efficiency by Surrogate Model-Based Optimization with Phenotypic Distance Kernels
In NeuroEvolution, the topologies of artificial neural networks are optimized with evolutionary algorithms to solve tasks in data regression, data classification, or reinforcement learning. One downside of NeuroEvolution is the large amount of necessary fitness evaluations, which might render it inefficient for tasks with expensive evaluations, such as real-time learning. For these expensive optimization tasks, surrogate model-based optimization is frequently applied as it features a good evaluation efficiency. While a combination of both procedures appears as a valuable solution, the definition of adequate distance measures for the surrogate modeling process is difficult. In this study, we will extend cartesian genetic programming of artificial neural networks by the use of surrogate model-based optimization. We propose different distance measures and test our algorithm on a replicable benchmark task. The results indicate that we can significantly increase the evaluation efficiency and that a phenotypic distance, which is based on the behavior of the associated neural networks, is most promising.
KeywordsNeuroevolution Surrogate models Kernel Distance Optimization
This work is supported by the German Federal Ministry of Education and Research in the funding program Forschung an Fachhochschulen under the grant number 13FH007IB6.
- 4.Turner, A.J., Miller, J.F.: Cartesian genetic programming encoded artificial neural networks: a comparison using three benchmarks. In: Proceedings of GECCO 2013, pp. 1005–1012. ACM (2013)Google Scholar
- 7.Zaefferer, M., Stork, J., Friese, M., Fischbach, A., Naujoks, B., Bartz-Beielstein, T.: Efficient global optimization for combinatorial problems. In: Proceedings of GECCO 2014, pp. 871–878. ACM (2014)Google Scholar
- 8.Stork, J., Zaefferer, M., Bartz-Beielstein, T.: Distance-based kernels for surrogate model-based neuroevolution. arXiv preprint arXiv:1807.07839 (2018)
- 9.Zaefferer, M., Stork, J., Flasch, O., Bartz-Beielstein, T.: Linear combination of distance measures for surrogate models in genetic programming. In: Auger, A., Fonseca, C.M., Lourenço, N., Machado, P., Paquete, L., Whitley, D. (eds.) PPSN 2018. LNCS, vol. 11102, pp. 220–231. Springer, Cham (2018). https://doi.org/10.1007/978-3-319-99259-4_18CrossRefGoogle Scholar
- 10.Gaier, A., Asteroth, A., Mouret, J.B.: Data-efficient neuroevolution with kernel-based surrogate models. In: Genetic and Evolutionary Computation Conference (GECCO) (2018)Google Scholar
- 12.Stork, J., Bartz-Beielstein, T., Fischbach, A., Zaefferer, M.: Surrogate assisted learning of neural networks. In: GMA CI-Workshop 2017 (2017)Google Scholar
- 16.Mockus, J., Tiesis, V., Zilinskas, A.: The application of Bayesian methods for seeking the extremum. In: Towards Global Optimization 2, North-Holland, pp. 117–129 (1978)Google Scholar